Contrastive Learning Guided Latent Diffusion Model for Image-to-Image Translation

원문 초록

The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the preservation of reference image content. First, variations in target text prompts can significantly influence the quality of the generated images, and it is often challenging for users to craft an optimal prompt that fully captures the content of the input image. Second, while existing models can introduce desired modifications to specific regions of the reference image, they frequently induce unintended alterations in areas that should remain unchanged. To address these challenges, we propose pix2pix-zeroCon, a zero-shot diffusion-based method that eliminates the need for additional training by leveraging patch-wise contrastive loss. Specifically, we automatically determine the editing direction in the text embedding space based on the reference image and target prompts. Furthermore, to ensure precise content and structural preservation in the edited image, we introduce cross-attention guiding loss and patch-wise contrastive loss between the generated and original image embeddings within a pre-trained diffusion model. Notably, our approach requires no additional training and operates directly on a pre-trained text-to-image diffusion model. Extensive experiments demonstrate that our method surpasses existing models in image-to-image translation, achieving enhanced fidelity and controllability.